Re:Apple: Transformer architecture optimized for Apple Silicon
by endisneigh on Thursday March 23, 2023 @07:24PM
(#35282943)
right, that's why I mentioned performance at the current level at far less compute, and not necessarily better performance.
Almost 5 years ago TalkToTransformer did 80% of ChatGPT's job with 0% of the hype. Once people realize just how glacial all this stuff moves, I think the honeymoon phase will be over.